Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interaction
    -0.07
     fac
    -0.07
     alerts
    -0.07
    central
    -0.07
     space
    -0.07
    _shift
    -0.07
     basal
    -0.06
    mid
    -0.06
    -search
    -0.06
     forwarded
    -0.06
    POSITIVE LOGITS
    นม
    0.07
    Strange
    0.06
    Doing
    0.06
    (hero
    0.06
    �
    0.06
     moderne
    0.06
     reife
    0.06
    ,.↵↵
    0.06
    ，在
    0.06
    зм
    0.06
    Act Density 0.273%

    No Known Activations